© 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. 869
    Prev
    Next
    INDEX
    Explanations

    phrases related to researchers, profiles, and people in various contexts

    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
    1919
    +0.18
    0.5%
    783
    +0.07
    0.2%
    227
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1919
    +0.18
    0.09
    862
    +0.07
    0.04
    513
    +0.07
    0.04
    Negative Logits
     nutr
    -1.54
     mef
    -1.51
     ordina
    -1.45
     nomine
    -1.45
     buc
    -1.44
     ivi
    -1.42
     maroc
    -1.38
     socie
    -1.38
     centrif
    -1.36
     pira
    -1.36
    POSITIVE LOGITS
     can
    1.05
     cannot
    1.02
     could
    1.00
     might
    0.96
     may
    0.95
     will
    0.93
     should
    0.92
     would
    0.90
     couldn
    0.86
     shouldn
    0.85
    Activations Density 0.424%

    No Known Activations