© 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. 3404
    Prev
    Next
    INDEX
    Explanations

    discussion on decision-making related to potential consequences or outcomes

    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
    1967
    +0.09
    0.3%
    1473
    +0.08
    0.2%
    1343
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1424
    +0.09
    0.02
    1450
    +0.08
    0.02
    1820
    +0.08
    0.02
    Negative Logits
     „,
    -0.89
     stockholm
    -0.87
     wien
    -0.81
     oleo
    -0.78
     erec
    -0.78
     drey
    -0.78
     riviera
    -0.77
     tulum
    -0.77
     impati
    -0.77
     lidl
    -0.77
    POSITIVE LOGITS
    <?
    0.53
     not
    0.49
    not
    0.48
    bdb
    0.46
     satunya
    0.46
    leukin
    0.46
    NOPE
    0.44
    AndWait
    0.44
    verdad
    0.43
    dfd
    0.43
    Activations Density 0.064%

    No Known Activations