© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 6613
    Prev
    Next
    INDEX
    Explanations

    mentions of the search for life or organisms in various contexts, including in space, specifically related to Mars

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    2015
    +0.13
    0.4%
    1253
    +0.11
    0.3%
    752
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    875
    +0.13
    0.03
    152
    +0.11
    0.04
    471
    +0.10
    0.02
    Negative Logits
     karton
    -0.81
     akut
    -0.60
     Managua
    -0.58
     balkon
    -0.57
     kosme
    -0.55
     compréhen
    -0.55
     hoody
    -0.55
     Pamplona
    -0.54
     youtuber
    -0.53
     volon
    -0.53
    POSITIVE LOGITS
     getenv
    0.55
     potentiel
    0.46
     parámetros
    0.46
     strto
    0.45
     atof
    0.45
     cálculos
    0.44
     civilizations
    0.44
     habitable
    0.44
    ophiles
    0.44
     planetas
    0.44
    Activations Density 0.370%

    No Known Activations