© 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. 14568
    Prev
    Next
    INDEX
    Explanations

    names of individuals

    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
    1343
    +0.19
    0.6%
    394
    +0.12
    0.4%
    1120
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.19
    0.09
    227
    +0.12
    0.07
    1314
    +0.11
    0.06
    Negative Logits
     ład
    -0.64
     cancerous
    -0.63
     createdAt
    -0.60
     indigestion
    -0.60
     festgelegt
    -0.59
     injurious
    -0.59
    FORMANCE
    -0.59
     einheit
    -0.58
     sterility
    -0.58
     secretions
    -0.58
    POSITIVE LOGITS
     Février
    1.58
     quoique
    1.45
     Sén
    1.43
     |]
    1.43
     Secrétaire
    1.35
     Juillet
    1.33
     Chapitre
    1.33
     Lég
    1.33
     §.
    1.33
     simplif
    1.32
    Activations Density 0.315%

    No Known Activations