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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7514
    Prev
    Next
    INDEX
    Explanations

    text related to news articles or reports on various topics, including sports, cryptocurrency, accidents, politics, and discoveries

    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
    892
    +0.15
    0.5%
    553
    +0.13
    0.5%
    1363
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    553
    +0.15
    0.04
    1527
    +0.13
    0.04
    214
    +0.13
    0.03
    Negative Logits
     wolverine
    -0.57
     beatles
    -0.55
     nigger
    -0.53
     easter
    -0.53
     motherfucker
    -0.52
     pelican
    -0.51
    subaru
    -0.51
     wwe
    -0.51
     pamph
    -0.50
     godfather
    -0.49
    POSITIVE LOGITS
     maksi
    0.92
     kac
    0.83
     silikon
    0.81
     bunda
    0.80
     persil
    0.77
     akut
    0.77
     keramik
    0.75
     kön
    0.75
     kompati
    0.75
     karton
    0.75
    Activations Density 0.111%

    No Known Activations