© 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. 1028
    Prev
    Next
    INDEX
    Explanations

    references to financial figures and economic indicators

    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
    674
    +0.10
    0.3%
    1385
    +0.10
    0.3%
    1445
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1460
    +0.10
    0.03
    181
    +0.10
    0.03
    609
    +0.10
    0.02
    Negative Logits
     sputnik
    -0.84
     Vn
    -0.81
     Fg
    -0.80
     wien
    -0.78
     Vc
    -0.77
     Bx
    -0.76
     tph
    -0.75
     Lc
    -0.75
     juven
    -0.74
     illi
    -0.73
    POSITIVE LOGITS
     roughly
    0.62
    rlrl
    0.60
     equivalent
    0.59
    Ikr
    0.56
     approximately
    0.54
    mistak
    0.54
    roughly
    0.53
    Jeez
    0.52
     cuida
    0.52
    deutung
    0.52
    Activations Density 0.143%

    No Known Activations