© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 1102
    Prev
    Next
    INDEX
    Explanations

    references to the use of spells

    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
    893
    +0.16
    0.7%
    1482
    +0.15
    0.6%
    481
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1256
    +0.16
    0.02
    481
    +0.15
    0.02
    68
    +0.14
    0.02
    Negative Logits
     lenker
    -0.59
     الحره
    -0.58
    ConstraintMaker
    -0.57
    KURZBESCHREIBUNG
    -0.53
    ējās
    -0.52
    PDOException
    -0.52
    Litteratur
    -0.51
    andaş
    -0.50
    uxxxx
    -0.50
    djangoproject
    -0.49
    POSITIVE LOGITS
     spell
    1.24
     spells
    1.20
    spells
    1.12
     Spell
    1.10
    spell
    1.08
     Spells
    1.07
    Spell
    0.97
     bandung
    0.88
     spelled
    0.87
    Spells
    0.86
    Activations Density 0.092%

    No Known Activations