© 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. 13809
    Prev
    Next
    INDEX
    Explanations

    instances of phrases related to personal growth and self-reflection

    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
    1978
    +0.17
    0.5%
    1013
    +0.13
    0.4%
    1842
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.17
    0.09
    2044
    +0.13
    0.09
    1013
    +0.09
    0.08
    Negative Logits
     vogli
    -1.17
     poichè
    -1.16
     sappi
    -1.14
     jorge
    -1.07
     Cfr
    -1.07
     javier
    -1.07
     ricardo
    -1.06
     sergio
    -1.06
     inol
    -1.05
     felipe
    -1.05
    POSITIVE LOGITS
    .
    0.68
    ,
    0.63
     stuff
    0.62
    transQ
    0.60
     and
    0.60
     because
    0.59
     really
    0.59
     of
    0.59
    ,"
    0.59
     when
    0.59
    Activations Density 0.759%

    No Known Activations