© 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. 2468
    Prev
    Next
    INDEX
    Explanations

    economic or financial terms and discussions

    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
    604
    +0.12
    0.3%
    1531
    +0.08
    0.2%
    1796
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1796
    +0.12
    0.04
    1159
    +0.08
    0.03
    1477
    +0.07
    0.04
    Negative Logits
     reluct
    -0.96
     apprehen
    -0.94
     unspeak
    -0.92
    <bos>
    -0.92
     shenan
    -0.90
     gaily
    -0.88
     disagre
    -0.85
     indestru
    -0.82
     encomp
    -0.81
     obstin
    -0.81
    POSITIVE LOGITS
     drawbacks
    0.63
    ErrorListener
    0.61
    NegativeButton
    0.61
     downside
    0.60
    VolleyError
    0.55
     disadvantages
    0.55
    easeOut
    0.55
     drawback
    0.54
     שוליים
    0.54
     vice
    0.53
    Activations Density 0.398%

    No Known Activations