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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 10134
    Prev
    Next
    INDEX
    Explanations

    information related to criminal activities, news, and recipes

    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
    1013
    +0.18
    0.6%
    736
    +0.13
    0.4%
    876
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1551
    +0.18
    0.05
    736
    +0.13
    0.07
    753
    +0.13
    0.01
    Negative Logits
     gubern
    -1.00
     monaster
    -1.00
     ecclesias
    -0.81
     Erlangen
    -0.79
     Riau
    -0.79
     Bochum
    -0.76
     Banten
    -0.75
     ideolog
    -0.75
     meras
    -0.74
     gentes
    -0.74
    POSITIVE LOGITS
     shenan
    1.43
     increa
    1.24
     impra
    1.24
     scrat
    1.21
     reluct
    1.19
     affor
    1.18
     snoopy
    1.18
     disagre
    1.13
     intersper
    1.12
     cushi
    1.12
    Activations Density 0.495%

    No Known Activations