© 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. 3307
    Prev
    Next
    INDEX
    Explanations

    phrases related to analyzing and discussing various aspects of science, technology, and society

    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
    872
    +0.18
    0.6%
    50
    +0.10
    0.3%
    1871
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    872
    +0.18
    0.09
    1380
    +0.10
    0.02
    1477
    +0.09
    0.07
    Negative Logits
     Kese
    -0.65
     mikrofon
    -0.60
    Rhestr
    -0.56
     internetu
    -0.55
     karton
    -0.55
     sicura
    -0.53
    TypedDataSet
    -0.53
     pitié
    -0.52
    ₵
    -0.52
     terv
    -0.51
    POSITIVE LOGITS
     hairc
    0.74
     Whence
    0.63
     swee
    0.59
    newVal
    0.59
     silken
    0.57
     linden
    0.57
     poul
    0.57
     asht
    0.57
     cuban
    0.56
     handker
    0.56
    Activations Density 0.768%

    No Known Activations