© 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. 12821
    Prev
    Next
    INDEX
    Explanations

    expressions related to desire or intention to do something

    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
    438
    +0.13
    0.4%
    906
    +0.08
    0.2%
    1927
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.13
    0.07
    1262
    +0.08
    0.04
    991
    +0.07
    0.04
    Negative Logits
     Kün
    -0.78
     unspeak
    -0.72
     Intere
    -0.71
     disagre
    -0.68
     endeavouring
    -0.68
     apprehen
    -0.68
     Schrö
    -0.67
     tolerably
    -0.67
     Pfal
    -0.66
     Sarm
    -0.66
    POSITIVE LOGITS
     bonté
    0.74
     jajaja
    0.67
     gioielli
    0.66
    ">/
    0.64
     aspetta
    0.60
     eccl
    0.59
     pensieri
    0.59
     costumi
    0.59
     righe
    0.58
     vestiti
    0.57
    Activations Density 0.321%

    No Known Activations