© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 13784
    Prev
    Next
    INDEX
    Explanations

    names of people and references to personal relationships or events involving those people being accused or convicted of various actions

    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
    1842
    +0.39
    1.3%
    184
    +0.23
    0.8%
    1967
    +0.20
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1842
    +0.39
    0.06
    227
    +0.23
    0.06
    856
    +0.20
    0.03
    Negative Logits
     nélk
    -0.50
     physiologic
    -0.45
    createdDate
    -0.44
     mę
    -0.44
     chłop
    -0.43
     ddelweddau
    -0.42
     infographics
    -0.42
     resear
    -0.41
     bł
    -0.41
     experiential
    -0.41
    POSITIVE LOGITS
     CiNii
    0.82
     quoique
    0.81
     Février
    0.81
     Giugno
    0.81
     Décembre
    0.80
     Cfr
    0.78
     charité
    0.78
     Portail
    0.77
     exé
    0.77
     nomme
    0.76
    Activations Density 0.261%

    No Known Activations