© 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. 1088
    Prev
    Next
    INDEX
    Explanations

    locations and neighborhoods within a city

    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
    964
    +0.21
    0.6%
    1013
    +0.19
    0.6%
    576
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    964
    +0.21
    0.07
    1013
    +0.19
    0.06
    227
    +0.09
    0.06
    Negative Logits
     scalars
    -0.60
    FTFY
    -0.59
     imparare
    -0.59
     cytok
    -0.56
     condividere
    -0.55
     aspetta
    -0.55
     Ottobre
    -0.51
     affez
    -0.50
     polypep
    -0.49
    Moist
    -0.49
    POSITIVE LOGITS
     neighborhood
    0.94
     neighborhoods
    0.93
    neighborhood
    0.79
     neighbourhood
    0.78
     Neighborhood
    0.75
     neighbourhoods
    0.72
    bourhood
    0.71
    Neighborhood
    0.66
    ighborhood
    0.64
     Gorb
    0.57
    Activations Density 0.344%

    No Known Activations