© 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. 1874
    Prev
    Next
    INDEX
    Explanations

    objects or things that can be physically interacted with

    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
    1013
    +0.16
    0.5%
    1177
    +0.11
    0.3%
    1870
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.16
    0.07
    289
    +0.11
    0.03
    249
    +0.10
    0.06
    Negative Logits
     alkoh
    -1.10
     meis
    -1.08
     lele
    -1.08
     uhr
    -1.07
     doman
    -1.05
     „,
    -1.04
     kram
    -1.04
     glan
    -1.04
     franz
    -1.04
     lü
    -1.02
    POSITIVE LOGITS
     containing
    0.67
     vedno
    0.65
    idać
    0.64
     placed
    0.62
     écrans
    0.60
    которы
    0.60
     leçons
    0.59
     located
    0.59
     whose
    0.58
     stuck
    0.58
    Activations Density 0.515%

    No Known Activations