© 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. 14566
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal or individual advancement and development

    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
    872
    +0.11
    0.3%
    882
    +0.09
    0.3%
    1013
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1853
    +0.11
    0.04
    2027
    +0.09
    0.04
    1755
    +0.09
    0.04
    Negative Logits
     alkoh
    -0.67
     Strukt
    -0.66
     pól
    -0.64
     Bakter
    -0.64
     Kombin
    -0.63
     praktik
    -0.60
    kontroll
    -0.59
     vermel
    -0.59
     republi
    -0.58
     minimalis
    -0.57
    POSITIVE LOGITS
     sondern
    1.05
     بلکه
    0.87
     nor
    0.84
     anymore
    0.82
     אלא
    0.80
    而是
    0.74
     melainkan
    0.74
     but
    0.69
     hanem
    0.67
    but
    0.66
    Activations Density 0.439%

    No Known Activations