Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 1152
    Prev
    Next
    INDEX
    Explanations

    website URLs

    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
    1140
    +0.15
    0.7%
    144
    +0.14
    0.6%
    1937
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1778
    +0.15
    0.04
    144
    +0.14
    0.03
    981
    +0.14
    0.04
    Negative Logits
     Bracken
    -0.56
     trattamento
    -0.47
     Paese
    -0.45
     Currie
    -0.44
     Mase
    -0.43
     Matthews
    -0.42
     stiamo
    -0.41
     Reiter
    -0.41
     Chel
    -0.41
     cervello
    -0.41
    POSITIVE LOGITS
     Vo
    1.02
     vo
    0.98
    Vo
    0.89
    vo
    0.78
     VO
    0.70
     voca
    0.66
    VO
    0.65
     pymysql
    0.64
     Volo
    0.63
     Cord
    0.62
    Activations Density 0.285%

    No Known Activations