© 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. 13826
    Prev
    Next
    INDEX
    Explanations

    sections referring to programming concepts, codes and technical details

    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
    1741
    +0.16
    0.5%
    468
    +0.14
    0.5%
    1177
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1288
    +0.16
    0.05
    468
    +0.14
    0.03
    1148
    +0.13
    0.03
    Negative Logits
     barbarous
    -0.69
     sceptre
    -0.67
     Whigs
    -0.64
     infernal
    -0.64
     warlike
    -0.64
     wretch
    -0.64
     fulness
    -0.63
     withal
    -0.63
     vicissitudes
    -0.62
     lamella
    -0.61
    POSITIVE LOGITS
    UnusedPrivate
    0.62
    hatenablog
    0.57
     <<<<<<<<<<<<<<
    0.56
     bezeichneter
    0.53
     مشين
    0.52
     sembla
    0.52
     identifiant
    0.51
    awtextra
    0.51
     كومونز
    0.51
     vnd
    0.51
    Activations Density 0.457%

    No Known Activations