© 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. 14331
    Prev
    Next
    INDEX
    Explanations

    instances where someone insists on something or emphasizes a particular point

    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
    1026
    +0.14
    0.5%
    204
    +0.13
    0.5%
    1677
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1026
    +0.14
    0.03
    204
    +0.13
    0.02
    1677
    +0.13
    0.02
    Negative Logits
     Strukt
    -0.80
     utop
    -0.75
     diabe
    -0.67
     praktik
    -0.67
     ohr
    -0.66
     makro
    -0.66
     akut
    -0.65
     minimalis
    -0.65
     puc
    -0.64
     Laus
    -0.64
    POSITIVE LOGITS
     insist
    1.03
     insisting
    0.93
     insisted
    0.91
     insists
    0.85
     insistence
    0.74
     insistent
    0.56
     insiste
    0.51
     erfre
    0.50
     persist
    0.49
     ļ
    0.49
    Activations Density 0.062%

    No Known Activations