© 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. 12883
    Prev
    Next
    INDEX
    Explanations

    names or words containing 'ss'

    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
    1624
    +0.14
    0.6%
    481
    +0.14
    0.6%
    1482
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.14
    0.05
    1624
    +0.14
    0.04
    481
    +0.13
    0.04
    Negative Logits
    Pä
    -0.58
    loài
    -0.52
    SourceChecksum
    -0.48
    archiviato
    -0.48
    Prie
    -0.47
     Unido
    -0.47
    Према
    -0.46
    Enciclopedia
    -0.46
    bingen
    -0.46
    hObject
    -0.45
    POSITIVE LOGITS
     noss
    1.24
     roberto
    1.17
     poff
    1.14
     vns
    1.11
     ftu
    1.09
     lorenzo
    1.08
     fernando
    1.07
     gabri
    1.07
     jorge
    1.06
     fays
    1.06
    Activations Density 0.245%

    No Known Activations