© 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. 3765
    Prev
    Next
    INDEX
    Explanations

    words related to suggestions or recommendations

    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
    1895
    +0.11
    0.3%
    1183
    +0.10
    0.3%
    1253
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    763
    +0.11
    0.04
    1183
    +0.10
    0.03
    261
    +0.10
    0.02
    Negative Logits
    Cormack
    -0.49
    essica
    -0.47
     startX
    -0.47
    Leod
    -0.45
    Dermott
    -0.45
     noOf
    -0.44
     hvem
    -0.44
     HasFactory
    -0.43
     updateTime
    -0.42
    leanor
    -0.42
    POSITIVE LOGITS
     katastro
    0.70
     kosme
    0.67
     stoff
    0.66
     konkre
    0.61
     hek
    0.60
     drap
    0.59
     silikon
    0.59
     asfal
    0.58
     plak
    0.58
     alkoh
    0.57
    Activations Density 0.131%

    No Known Activations