© 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. 12868
    Prev
    Next
    INDEX
    Explanations

    comparisons and differences

    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
    108
    +0.09
    0.3%
    1042
    +0.08
    0.2%
    282
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    310
    +0.09
    0.03
    584
    +0.08
    0.03
    3
    +0.08
    0.04
    Negative Logits
    ఔ
    -0.55
    PRNewswire
    -0.51
    matchCondition
    -0.48
    ubblica
    -0.45
    LOTTE
    -0.45
    tská
    -0.44
     conlle
    -0.44
    ждую
    -0.43
    Asimismo
    -0.43
    modb
    -0.43
    POSITIVE LOGITS
     theirs
    1.21
     hers
    1.11
     ours
    1.07
     Ours
    1.03
     yours
    0.96
     celui
    0.94
     thut
    0.92
     perfon
    0.92
     purcha
    0.91
     feen
    0.90
    Activations Density 0.245%

    No Known Activations