© 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. 13857
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a request for feedback or information sharing.

    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
    763
    +0.08
    0.2%
    1150
    +0.08
    0.2%
    1343
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    763
    +0.08
    0.03
    1056
    +0.08
    0.03
    1799
    +0.08
    0.01
    Negative Logits
     kram
    -0.89
     kupa
    -0.89
     makro
    -0.88
     alkoh
    -0.88
     lele
    -0.88
     akut
    -0.86
     karton
    -0.84
     silikon
    -0.84
     fua
    -0.83
     antik
    -0.82
    POSITIVE LOGITS
     how
    0.67
     whether
    0.65
     if
    0.60
     what
    0.57
     tell
    0.55
     any
    0.55
     your
    0.54
    whether
    0.52
     via
    0.52
     einander
    0.51
    Activations Density 0.136%

    No Known Activations