© 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. 13703
    Prev
    Next
    INDEX
    Explanations

    information related to incidents or accidents

    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
    50
    +0.17
    0.5%
    1577
    +0.11
    0.3%
    1013
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    856
    +0.17
    0.10
    227
    +0.11
    0.17
    50
    +0.10
    0.18
    Negative Logits
     bandung
    -0.77
     habet
    -0.77
     indeb
    -0.73
     potest
    -0.71
     haup
    -0.70
     bombe
    -0.69
     jaja
    -0.69
     dises
    -0.69
     dora
    -0.67
     eorum
    -0.66
    POSITIVE LOGITS
     Bartholo
    0.68
     McLaugh
    0.68
    stretchr
    0.66
     Bengt
    0.62
     XYZ
    0.62
     Defective
    0.60
     Rodrig
    0.59
     Punct
    0.59
     Vaugh
    0.59
     Gorb
    0.58
    Activations Density 5.217%

    No Known Activations