© 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. 3704
    Prev
    Next
    INDEX
    Explanations

    mentions of time periods or historical events

    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
    776
    +0.15
    0.4%
    1967
    +0.12
    0.4%
    1978
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    321
    +0.15
    0.07
    776
    +0.12
    0.06
    315
    +0.10
    0.05
    Negative Logits
     apprehen
    -1.04
     unspeak
    -0.94
     intersper
    -0.93
     shenan
    -0.93
     snoopy
    -0.90
     ineffec
    -0.90
     horrend
    -0.90
     stickied
    -0.87
     broadway
    -0.86
     gaily
    -0.84
    POSITIVE LOGITS
     utop
    1.02
     pól
    0.97
     monaster
    0.95
     inverte
    0.92
     asfal
    0.92
     antropo
    0.90
     elef
    0.90
     vola
    0.90
     balon
    0.88
     Antropo
    0.87
    Activations Density 0.131%

    No Known Activations