Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 14750
    Prev
    Next
    INDEX
    Explanations

    words related to starting and initiating actions or processes

    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
    1392
    +0.13
    0.5%
    1145
    +0.11
    0.4%
    554
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1392
    +0.13
    0.07
    1381
    +0.11
    0.05
    680
    +0.11
    0.04
    Negative Logits
    idenav
    -0.50
     vogliamo
    -0.49
     avevo
    -0.49
    ostante
    -0.47
     vediamo
    -0.47
     vorrei
    -0.45
     mData
    -0.44
     facciamo
    -0.43
     avete
    -0.42
     egli
    -0.42
    POSITIVE LOGITS
     start
    1.13
    start
    1.10
     START
    1.05
     Start
    1.05
    Start
    1.02
    START
    1.01
    started
    0.98
     started
    0.98
     starts
    0.98
     Starts
    0.93
    Activations Density 0.137%

    No Known Activations